From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: [PATCH][RESEND] tcp: replace hard coded GFP_KERNEL with sk_allocation Date: Wed, 02 Sep 2009 23:32:25 -0700 (PDT) Message-ID: <20090902.233225.203837229.davem@davemloft.net> References: <20090903040407.GA20094@localhost> <20090902.231017.31926895.davem@davemloft.net> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Cc: herbert-lOAM2aK0SrRLBo1qDEOMRrpzq4S04n8Q@public.gmane.org, acme-f8uhVLnGfZaxAyOMLChx1axOck334EZe@public.gmane.org, linux-kernel@vger.kernel.org, linux-nfs@vger.kernel.org, netdev@vger.kernel.org To: fengguang.wu@intel.com Return-path: Received: from 74-93-104-97-Washington.hfc.comcastbusiness.net ([74.93.104.97]:42674 "EHLO sunset.davemloft.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754535AbZICGcK (ORCPT ); Thu, 3 Sep 2009 02:32:10 -0400 In-Reply-To: <20090902.231017.31926895.davem@davemloft.net> Sender: linux-nfs-owner@vger.kernel.org List-ID: From: David Miller Date: Wed, 02 Sep 2009 23:10:17 -0700 (PDT) > From: Wu Fengguang > Date: Thu, 3 Sep 2009 12:04:07 +0800 > >> This fixed a lockdep warning which appeared when doing stress >> memory tests over NFS: >> >> inconsistent {RECLAIM_FS-ON-W} -> {IN-RECLAIM_FS-W} usage. >> >> page reclaim => nfs_writepage => tcp_sendmsg => lock sk_lock >> >> mount_root => nfs_root_data => tcp_close => lock sk_lock => >> tcp_send_fin => alloc_skb_fclone => page reclaim >> >> David raised a concern that if the allocation fails in tcp_send_fin(), and it's >> GFP_ATOMIC, we are going to yield() (which sleeps) and loop endlessly waiting >> for the allocation to succeed. >> >> But fact is, the original GFP_KERNEL also sleeps. GFP_ATOMIC+yield() looks >> weird, but it is no worse the implicit sleep inside GFP_KERNEL. Both could >> loop endlessly under memory pressure. >> >> CC: Arnaldo Carvalho de Melo >> CC: David S. Miller >> CC: Herbert Xu >> Signed-off-by: Wu Fengguang > > Applied to net-next-2.6, thanks! You obviously didn't build test this with TCP MD5 support enabled, that fails. I'm fixing it up, but if you're going to go through the motions of submitting a patch multiple times, at least do a thorough build test of the code you're changing.